Training in progress, epoch 1

config.json

@@ -4,6 +4,7 @@
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
+  "finetuning_task": "glue:mrpc",
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
@@ -14,7 +15,7 @@
   "max_position_embeddings": 512,
   "model_type": "bert",
   "num_attention_heads": 8,
-  "num_hidden_layers": 8,
+  "num_hidden_layers": 6,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",

logs/events.out.tfevents.1724864850.spartan-gpgpu092.hpc.unimelb.edu.au.158260.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:211d4ef08f918e3837948826e1482ca35f674d334a849c28ac61d81e14816080
+size 5525

logs/events.out.tfevents.1724864943.spartan-gpgpu092.hpc.unimelb.edu.au.160221.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8fb714d543fc4d8c0bd714520b02c68e3cec63f4cc0a77ee88108b45b369cb4
+size 5525

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78d6b7ad0ed0051719e5876c83854da563f62ede04988b4276f64a075510f2f8
-size 199099944
+oid sha256:dd309083e4b9477b62f220a43c403c40f3e87a069ede76a025502f6e573059e3
+size 165480304

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4133437389b9a80f735603a4fc80f75afad573ab0f46aeb6b900201c897ea6d4
+oid sha256:6dc0266cab8c87a628e1825ed0b2649c8d8b494ac42418da0f957b4a5e496968
 size 4984